全部能力

Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be…

Search 10 academic paper databases via REST APIs for research papers, preprints, and scholarly articles. Covers PubMed, PMC (full text), bioRxiv, medRxiv,…

Apply and enforce brand voice, style guide, and messaging pillars across content. Use when reviewing content for brand consistency, documenting a brand voice,…

Compares ideal plan vs existing tasks and applies KEEP/UPDATE/OBSOLETE/CREATE changes. Use when Story tasks need re-sync with updated requirements.

Build slide decks and presentations for research talks. Use this for making PowerPoint slides, conference presentations, seminar talks, research presentations,…

Creates design_guidelines.md with WCAG 2.1 compliance and design system docs. Use when project has a frontend.

Build stateful chatbots with OpenAI Assistants API v2 - Code Interpreter, File Search (10k files), Function Calling. Prevents 10 documented errors including vector store upload bugs, temperature parameter conflicts, memory leaks. Deprecated (sunset August 2026); use openai-responses for new projects. Use when: maintaining legacy chatbots, implementing RAG with vector stores, or troubleshooting thread errors, vector store delays, uploadAndPoll issues.

Creates reference docs (ADRs, guides, manuals) for nontrivial tech stack choices. Use when project needs justified architecture decision records.

Analyzes Story and builds optimal task plan (1-8 tasks), then routes to create or replan. Use when Story needs task breakdown or replanning.

Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage…

Generate and prioritize US equity long-side edge research tickets from EOD observations, then export pipeline-ready candidate specs for trade-strategy-pipeline…

Facilitate effective retrospectives to capture lessons learned, celebrate successes, and identify actionable improvements for future iterations.

Creates core project docs (requirements, architecture, tech stack, patterns catalog). Use for any project regardless of type.

Low-level plotting library for full customization. Use when you need fine-grained control over every plot element, creating novel plot types, or integrating…

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple…

Structured manuscript/grant review with checklist-based evaluation. Use when writing formal peer reviews with specific criteria methodology assessment,…

Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering,…

Retrieves and searches dbt documentation pages in LLM-friendly markdown format. Use when fetching dbt documentation, looking up dbt features, or answering…

Spawn Codex subagents via background shell to offload context-heavy work. Use for: deep research (3+ searches), codebase exploration (8+ files), multi-step workflows, exploratory tasks, long-running operations, documentation generation, or any other task where the intermediate steps will use large numbers of tokens.

Optimize cloud storage across AWS S3, Azure Blob, and GCP Cloud Storage with compression, partitioning, lifecycle policies, and cost management.